Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Finnish
whisper
whisper-event
finnish
Eval Results (legacy)
Instructions to use Finnish-NLP/whisper-medium-finnish with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Finnish-NLP/whisper-medium-finnish with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Finnish-NLP/whisper-medium-finnish")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Finnish-NLP/whisper-medium-finnish") model = AutoModelForSpeechSeq2Seq.from_pretrained("Finnish-NLP/whisper-medium-finnish", device_map="auto") - Notebooks
- Google Colab
- Kaggle
metadata
language:
- fi
license: apache-2.0
tags:
- whisper-event
- finnish
datasets:
- mozilla-foundation/common_voice_11_0
- google/fleurs
metrics:
- wer
- cer
model-index:
- name: Whisper Medium Finnish
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: fi
split: test
args: fi
metrics:
- name: Wer
type: wer
value: 12.01
- name: Cer
type: cer
value: 2.27
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: FLEURS
type: google/fleurs
config: fi_fi
split: test
args: fi_fi
metrics:
- name: Wer
type: wer
value: 10.96
- name: Cer
type: cer
value: 2.99